Techniques for generating magnetic resonance (MR) images of a subject from MR data obtained by a magnetic resonance imaging (MRI) system, the techniques including: obtaining input MR data obtained by imaging the subject using the MRI system; generating a plurality of transformed input MR data instances by applying a respective first plurality of transformations to the input MR data; generating a plurality of MR images from the plurality of transformed input MR data instances and the input MR data using a non-linear MR image reconstruction technique; generating an ensembled MR image from the plurality of MR images at least in part by: applying a second plurality of transformations to the plurality of MR images to obtain a plurality of transformed MR images; and combining the plurality of transformed MR images to obtain the ensembled MR image; and outputting the ensembled MR image.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection and representation in images. In one aspect, a method includes detecting occurrences of objects of a particular type in images captured within a first duration of time, and iteratively training an image embedding function to produce as output representations of features of the input images depicting occurrences of objects of the particular type, where similar representations of features are generated for images that depict the same instance of an object of a particular type captured within a specified duration of time, and dissimilar representations of features are generated for images that depict different instances of objects of the particular type.

A method of similarity-based deduplication comprising the steps of: receiving an input data block; computing discrete wavelet transform (DWT) coefficients; extracting feature-related DWT data from the computed DWT coefficients; applying quantization to the extracted feature-related DWT data to obtain keys as results of the quantization; constructing a locality-sensitive fingerprint of the input data block; computing a similarity degree between the locality-sensitive fingerprint of the input data block and a locality-sensitive fingerprint of each data block in the plurality of the data blocks in a cache memory; selecting an optimal reference data block as the data block; determining a differential compression is required to be applied based on the similarity degree between the input data block and the optimal reference data block; applying the differential compression to the input data block and the optimal reference data block.

A method includes obtaining a source training dataset that includes a plurality of source training images and obtaining a target training dataset that includes a plurality of target training images. For each source training image, the method includes translating, using the forward generator neural network G, the source training image to a respective translated target image according to current values of forward generator parameters. For each target training image, the method includes translating, using a backward generator neural network F, the target training image to a respective translated source image according to current values of backward generator parameters. The method also includes training the forward generator neural network G jointly with the backward generator neural network F by adjusting the current values of the forward generator parameters and the backward generator parameters to optimize an objective function.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an object embedding system. In one aspect, a method comprises providing selected images as input to the object embedding system and generating corresponding embeddings, wherein the object embedding system comprises a thumbnailing neural network and an embedding neural network. The method further comprises backpropagating gradients based on a loss function to reduce the distance between embeddings for same instances of objects, and to increase the distance between embeddings for different instances of objects.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying videos using neural networks. One of the methods includes obtaining a temporal sequence of video frames, wherein the temporal sequence comprises a respective video frame from a particular video at each of a plurality time steps; for each time step of the plurality of time steps: processing the video frame at the time step using a convolutional neural network to generate features of the video frame; and processing the features of the video frame using an LSTM neural network to generate a set of label scores for the time step and classifying the video as relating to one or more of the topics represented by labels in the set of labels from the label scores for each of the plurality of time steps.

A method and system has been provided for recommending features for developing an IoT analytics application. The method follows a deep like architecture. It comprises of three distinct layers. First layer is for input signal processing and other two layers are for feature reduction. The time domain, frequency domain and time-frequency domain features are extracted from the input signal. The invention uses multiple feature selection methods so that the union of the recommended features by these feature selection methods is significantly lesser than the initial set of features. The best feature combination is recommended using an exhaustive search.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection and representation in images. In one aspect, a method includes detecting occurrences of objects of a particular type in images captured within a first duration of time, and iteratively training an image embedding function to produce as output representations of features of the input images depicting occurrences of objects of the particular type, where similar representations of features are generated for images that depict the same instance of an object of a particular type captured within a specified duration of time, and dissimilar representations of features are generated for images that depict different instances of objects of the particular type.

A method of evaluating an image quality for an imaging system and the imaging system are provided. The method in some examples includes: acquiring an image to be evaluated which is generated by the imaging system; extracting a number of sub-images from the image; obtaining a coefficient vector indicating a degree of sparsity by applying a sparse decomposition on the sub-images based on a pre-set redundant sparse representation dictionary; and performing a linear transformation on the coefficient vector so as to obtain an evaluation value for the image quality. The sparse dictionary is learned by only using a few high quality perspective images, and then the image quality is evaluated based on the sparse degree of the image obtained by using the sparse dictionary. A convenient and rapid no-reference image quality evaluation is achieved.

To address the needs of applications that work with large-scale unstructured point clouds and other noisy data (e.g. image and video data), tangent convolution of 3D data represents 3D data as tangent planes. Tangent convolution estimates tangent planes for each 3D data point in one or more channels of 3D data. Tangent convolution further computes the tangent image signals for the estimated tangent planes. Tangent convolution precomputes the tangent planes and tangent image signals to enable convolution to be performed with greater efficiency and better performance than can be achieved with other 3D data representations.